© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90139
    Prev
    Next
    INDEX
    Explanations

    utopian future, output device, airline partner

    np_acts-logits-general · gemini-2.5-flash-lite

    lists and elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ې
    0.48
     ܘ
    0.47
     required
    0.46
     requisite
    0.46
     chiq
    0.46
     needed
    0.45
     grabbed
    0.45
     wirelessly
    0.45
     déi
    0.45
    日から
    0.44
    POSITIVE LOGITS
    Conservative
    0.50
    愷
    0.48
    Periods
    0.47
    arda
    0.46
    <unused70>
    0.46
    ندوق
    0.45
    <unused20>
    0.44
    筱
    0.44
    advertising
    0.44
    鄀
    0.43
    Activations Density 0.001%

    No Known Activations